🔥The 9th Round of Easy Loan, Earn $40 Reward is in progress❗️ ⏰ Promotion Period: January 15th - Feburary 15th, 2025 👉 Register now and check more details at gate.io/campaigns/358

Good benchmark scores are one thing but don't come close to models actually performing well in the wild. Kudos Markus Frohmann for a super useful release.

Excited to share that I joined ETH Zürich Zürich as a summer research fellow, supervised by Prof. @ryandcotterell, working on ✨Multimodal LLMs! ✨ The first few weeks have been a blast, and I'm looking forward to the weeks ahead! 📽️

This got accepted to #EMNLP 24 Main! ✨ Same goes for our paper on unsupervised debiasing 🤓 ✈️🇺🇲

Just in time for acceptance to #EMNLP2024, we added ONNX support to SaT🚀 The 12 layer model can now segment 45k chars in ~137ms. This is faster than the previous 3 layer model implementation.

Congratulations to C4AI Research Grant recipient Markus Frohmann and all authors of "Segment Any Text: A Universal Approach for Robust, Efficient and Adaptable Sentence Segmentation" for their EMNLP acceptance!🥳

This was an awesome summer! I can only recommend ETH's summer research fellowship program 🏔️ Also happy about the project's progress - integrating videos into existing architectures is quite exciting, stay tuned! Super grateful to Ryan Cotterell and Mario Giulianelli for supervising me.

Excited to share that I joined Deezer Research as a research intern to work with Elena V. Epure and Gabriel Meseguer on detecting AI-generated lyrics !🎶 The first few weeks have been amazing, and I am excited about what is to come—life in Paris certainly has unparalleled charm!

Curious about our SoTA text segmentation tool? 🪓 It's gonna help you across all kinds of NLP tasks! Learn more at our poster session: Tuesday, 4pm, Jasmine room at #EMNLP2024! 🗓️ See you there! I'll be attending the whole conference - happy to connect with everyone! 👋

We created Approximate Likelihood Matching, a principled (and very effective) method for *cross-tokenizer distillation*! With ALM, you can create ensembles of models from different families, convert existing subword-level models to byte-level and a bunch more🧵

Wtpsplit, our text segmentation tool, just reached ⭐️1000 stars⭐️ on GitHub! Excited to see it is proving useful! Check it out here: github.com/segment-any-te… 🎉